Generalization by learning is an essential cognitive competency for humans. For example, we can manipulate even unfamiliar objects and can generate mental images before enacting a preplan. How is this possible? Our study investigated this problem by revisiting our previous study (Jung, Matsumoto, & Tani, 2019), which examined the problem of vision-based, goal-directed planning by robots performing a task of block stacking. By extending the previous study, our work introduces a large network comprising dynamically interacting submodules, including visual working memory (VWMs), a visual attention module, and an executive network. The executive network predicts motor signals, visual images, and various controls for attention, as well as masking of visual information. The most significant difference from the previous study is that our current model contains an additional VWM. The entire network is trained by using predictive coding and an optimal visuomotor plan to achieve a given goal state is inferred using active inference. Results indicate that our current model performs significantly better than that used in Jung et al. (2019), especially when manipulating blocks with unlearned colors and textures. Simulation results revealed that the observed generalization was achieved because content-agnostic information processing developed through synergistic interaction between the second VWM and other modules during the course of learning, in which memorizing image contents and transforming them are dissociated. This letter verifies this claim by conducting both qualitative and quantitative analysis of simulation results.

通过学习进行泛化是人类必不可少的认知能力。例如，我们甚至可以操纵不熟悉的对象，并且可以在制定预案之前生成心理图像。这怎么可能？我们的研究通过回顾我们之前的研究（Jung、Matsumoto 和 Tani，2019 年）来调查这个问题，该研究检查了机器人执行块堆叠任务时基于视觉、目标导向的规划问题。通过扩展之前的研究，我们的工作引入了一个包含动态交互子模块的大型网络，包括视觉工作记忆 (VWM)、视觉注意模块和执行网络。执行网络预测运动信号、视觉图像和各种注意力控制，以及视觉信息的掩蔽。与之前的研究最显着的区别是我们当前的模型包含一个额外的 VWM。整个网络通过使用预测编码进行训练，并使用主动推理推断出实现给定目标状态的最佳视觉运动计划。结果表明，我们当前的模型的性能明显优于 Jung 等人使用的模型。(2019)，尤其是在操作具有未学习颜色和纹理的块时。仿真结果表明，观察到的泛化是因为在学习过程中通过第二个 VWM 和其他模块之间的协同交互发展的内容不可知信息处理，其中记忆图像内容和转换它们是分离的。